Bitte melden Sie sich an um selbst Rezensionen oder Kommentare zu erstellen.
Zitieren Sie diese Publikation
Mehr Zitationsstile
- bitte auswählen -
%0 Conference Paper
%1 conf/icml/Lancewicki0S23
%A Lancewicki, Tal
%A Rosenberg, Aviv
%A Sotnikov, Dmitry
%B ICML
%D 2023
%E Krause, Andreas
%E Brunskill, Emma
%E Cho, Kyunghyun
%E Engelhardt, Barbara
%E Sabato, Sivan
%E Scarlett, Jonathan
%I PMLR
%K dblp
%P 18482-18534
%T Delay-Adapted Policy Optimization and Improved Regret for Adversarial MDP with Delayed Bandit Feedback.
%U http://dblp.uni-trier.de/db/conf/icml/icml2023.html#Lancewicki0S23
%V 202
@inproceedings{conf/icml/Lancewicki0S23,
added-at = {2023-08-28T00:00:00.000+0200},
author = {Lancewicki, Tal and Rosenberg, Aviv and Sotnikov, Dmitry},
biburl = {https://www.bibsonomy.org/bibtex/2c1e82230442a22921df8091861d1654f/dblp},
booktitle = {ICML},
crossref = {conf/icml/2023},
editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan},
ee = {https://proceedings.mlr.press/v202/lancewicki23a.html},
interhash = {ad28dc4700715a79a4d03a4e6c63f79f},
intrahash = {c1e82230442a22921df8091861d1654f},
keywords = {dblp},
pages = {18482-18534},
publisher = {PMLR},
series = {Proceedings of Machine Learning Research},
timestamp = {2024-04-10T01:43:32.000+0200},
title = {Delay-Adapted Policy Optimization and Improved Regret for Adversarial MDP with Delayed Bandit Feedback.},
url = {http://dblp.uni-trier.de/db/conf/icml/icml2023.html#Lancewicki0S23},
volume = 202,
year = 2023
}